Paper Info
Title
Analysis-by-synthesis frame dropping algorithm together with a novel speech recognizer using time-varying hidden Markov model
Abstract
In distributed speech recognition applications, variable frame rate (VFR) analysis is a technique that can reduce the channel bandwidth and computation resources. In this method, slowly changing frames that provide little information are abandoned. Rapidly changing frames, on the other hand, that are more related to speech perception are preserved. In this paper, we proposed an analysis-by-synthesis (AbS) frame dropping algorithm together with a novel VFR decoding method for hidden Markov modeling of speech. A recursive formula for the calculation of forward probability function of the VFR observations was derived and was used to form a time-varying hidden Markov model (tvHMM) with transition probabilities that are depended on the time difference between successive observations. A generalized Viterbi decoding algorithm was developed to decode the VFR observations. We also use an example to explain the decoding process for a particular VFR observation sequence. Experiments were conducted to investigate the effectiveness of the proposed AbS-tvHMM method. The experimental results show that our method can achieve essentially the same accuracy as full frame rate observations at frame rate of only 40 % and significantly reduces the computation time.
Year
DOI
Venue
2014
10.1109/SMC.2014.6974268
SMC
Keywords
Field
DocType
hidden markov model (hmm),recursive formula,time-varying hidden markov model,viterbi decoding algorithm,speech recognition,vfr decoding method,time-varying systems,speech perception,abs frame dropping algorithm,distributed speech recognition applications,transition probabilities,variable frame rate (vfr),hidden markov speech modeling,viterbi decoding,distributed speech recognition,analysis-by-synthesis frame dropping algorithm,variable frame rate analysis,variable rate codes,vfr analysis,speech coding,forward probability function,recursive estimation,viterbi algorithm,channel bandwidth reduction,abs-tvhmm method,hidden markov models,probability,speech recognizer
Speech coding,Forward algorithm,Markov model,Soft output Viterbi algorithm,Computer science,Algorithm,Speech recognition,Artificial intelligence,Hidden Markov model,Iterative Viterbi decoding,Viterbi algorithm,Machine learning
Conference
ISSN
Citations 
PageRank 
1062-922X
1
0.36
References 
Authors
7
2
Name
Order
Citations
PageRank
Lee-Min Lee1468.10
Fu-Rong Jean2369.04